A two-stage kernel eigenfeature plus ridge estimator recovers fast labeled-sample rates in semi-supervised regression when proxy noise is controlled and unlabeled proxies are abundant, with the same guarantees for distribution regression.
arXiv preprint arXiv:1611.03787 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
A two-stage kernel eigenfeature plus ridge estimator recovers fast labeled-sample rates in semi-supervised regression when proxy noise is controlled and unlabeled proxies are abundant, with the same guarantees for distribution regression.